Qwen3.8: long context starts with a memory plan
A practical look at the Qwen3.8 27B catalog entry: stored weights, context settings and what to check before a local run.
AI workbench
Check what fits your computer.
Model
Hardware
Weight precision
Context window
Estimated memory Room to spare
6.7 / 23.0 GiB
needed / available after reserve
- Model weights
- 5.4 GiB
- Conversation memory
- 0.3 GiB
- Runtime allowance
- 1.0 GiB
Model details with source evidence.
Gemma 4 E2B: read beyond the small-model label
The stored checkpoint matters when planning memory. Here is how to turn a compact-model headline into a useful hardware check.
Mixture of experts: active parameters are only part of the story
Gemma 4 26B-A4B is a useful example of why compute-oriented model labels and a local memory budget answer different questions.
Five lessons, from the basics to a first run.
- 01
Models
Tell a model, a model file and a runtime apart.
- 02
Memory
Distinguish memory capacity from usable memory and speed.
- 03
Precision
Explain the memory tradeoff behind Q4, Q8 and FP16.
- 04
Context
Connect tokens and simultaneous conversations to memory use.
- 05
Run & verify
Check compatibility, answer quality and speed separately.
Setup & troubleshooting
All guides ↗Ollama hardware requirements: how much RAM and VRAM do you need?
Plan Ollama RAM and VRAM for 8GB, 12GB, 16GB and 24GB GPUs. Compare worked model-memory examples and check GPU offloading before buying hardware.
Ollama vs LM Studio: which should you use for local AI?
Compare Ollama and LM Studio for local chat, APIs, offline use and Mac runtimes. Choose by workflow, then test the same model and memory settings.
How much Mac memory do you need for local LLMs?
Compare 16GB, 24GB, 32GB and 64GB Mac memory for local LLMs. Budget unified memory, context and macOS headroom with worked model examples.
Why is my local LLM so slow?
Troubleshoot slow Ollama, LM Studio and llama.cpp inference. Separate loading, prompt processing and generation before changing hardware.
Why your local LLM runs out of memory in longer chats
Fix local LLM out-of-memory errors as context grows. Budget the KV cache, reduce concurrency and test cache quantization without losing key information.
Smaller Q8 or larger Q4: which local model should you run?
Choose between a smaller high-precision LLM and a larger quantized model with a practical test for quality, memory, context and response time.
Local RAG giving bad answers? Check retrieval first.
Fix local document Q&A with a practical RAG checklist: PDF extraction, chunks, embeddings, hybrid search, reranking and a small evaluation set.